tutorials/025 - Redshift - Loading Parquet files with Spectrum.ipynb (463 lines of code) (raw):
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"[![AWS SDK for pandas](_static/logo.png \"AWS SDK for pandas\")](https://github.com/aws/aws-sdk-pandas)\n",
"\n",
"# 25 - Redshift - Loading Parquet files with Spectrum"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Enter your bucket name:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Install the optional modules first\n",
"!pip install 'awswrangler[redshift]'"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ···········································\n"
]
}
],
"source": [
"import getpass\n",
"\n",
"bucket = getpass.getpass()\n",
"PATH = f\"s3://{bucket}/files/\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Mocking some Parquet Files on S3"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>col0</th>\n",
" <th>col1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>5</td>\n",
" <td>f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>6</td>\n",
" <td>g</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>7</td>\n",
" <td>h</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>8</td>\n",
" <td>i</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>9</td>\n",
" <td>j</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" col0 col1\n",
"0 0 a\n",
"1 1 b\n",
"2 2 c\n",
"3 3 d\n",
"4 4 e\n",
"5 5 f\n",
"6 6 g\n",
"7 7 h\n",
"8 8 i\n",
"9 9 j"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"import awswrangler as wr\n",
"\n",
"df = pd.DataFrame(\n",
" {\n",
" \"col0\": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],\n",
" \"col1\": [\"a\", \"b\", \"c\", \"d\", \"e\", \"f\", \"g\", \"h\", \"i\", \"j\"],\n",
" }\n",
")\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"wr.s3.to_parquet(df, PATH, max_rows_by_file=2, dataset=True, mode=\"overwrite\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Crawling the metadata and adding into Glue Catalog"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"({'col0': 'bigint', 'col1': 'string'}, None, None)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"wr.s3.store_parquet_metadata(path=PATH, database=\"aws_sdk_pandas\", table=\"test\", dataset=True, mode=\"overwrite\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Running the CTAS query to load the data into Redshift storage"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"con = wr.redshift.connect(connection=\"aws-sdk-pandas-redshift\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"query = \"CREATE TABLE public.test AS (SELECT * FROM aws_sdk_pandas_external.test)\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"with con.cursor() as cursor:\n",
" cursor.execute(query)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Running an INSERT INTO query to load MORE data into Redshift storage"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame(\n",
" {\n",
" \"col0\": [10, 11],\n",
" \"col1\": [\"k\", \"l\"],\n",
" }\n",
")\n",
"wr.s3.to_parquet(df, PATH, dataset=True, mode=\"overwrite\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"query = \"INSERT INTO public.test (SELECT * FROM aws_sdk_pandas_external.test)\""
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"with con.cursor() as cursor:\n",
" cursor.execute(query)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Checking the result"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"query = \"SELECT * FROM public.test\""
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>col0</th>\n",
" <th>col1</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5</td>\n",
" <td>f</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>b</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>d</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6</td>\n",
" <td>g</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>8</td>\n",
" <td>i</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>10</td>\n",
" <td>k</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>4</td>\n",
" <td>e</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0</td>\n",
" <td>a</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>2</td>\n",
" <td>c</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>7</td>\n",
" <td>h</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>9</td>\n",
" <td>j</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>11</td>\n",
" <td>l</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" col0 col1\n",
"0 5 f\n",
"1 1 b\n",
"2 3 d\n",
"3 6 g\n",
"4 8 i\n",
"5 10 k\n",
"6 4 e\n",
"7 0 a\n",
"8 2 c\n",
"9 7 h\n",
"10 9 j\n",
"11 11 l"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"wr.redshift.read_sql_table(con=con, schema=\"public\", table=\"test\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"con.close()"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.9.14",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.14"
},
"pycharm": {
"stem_cell": {
"cell_type": "raw",
"metadata": {
"collapsed": false
},
"source": []
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}